Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8399
    Prev
    Next
    INDEX
    Explanations

    occurrences of callback functions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     élas
    -0.59
     päät
    -0.57
     universale
    -0.57
     nationaux
    -0.56
     noires
    -0.56
    日閲覧
    -0.56
     anteriore
    -0.56
     démocr
    -0.54
     relatifs
    -0.53
     esterna
    -0.52
    POSITIVE LOGITS
     country
    0.96
     callback
    0.95
     callbacks
    0.88
     countryside
    0.87
     useAppContext
    0.85
    TintMode
    0.84
     Country
    0.84
     COUNTRY
    0.82
     дописавши
    0.81
     Greens
    0.80
    Activations Density 0.138%

    No Known Activations